© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 3987
    Prev
    Next
    INDEX
    Explanations

    mentions of the political party "Lib Dems"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Liberal Democrats political party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.75
     Oaks
    -0.72
    ãĤĤ
    -0.70
     Firefly
    -0.66
    HAHA
    -0.66
    OHN
    -0.66
    à¨
    -0.66
     Dragonbound
    -0.65
    à
    -0.65
     Solo
    -0.63
    POSITIVE LOGITS
     Lib
    1.11
    Lib
    1.06
    virt
    0.98
    ido
    0.92
    ombo
    0.84
    aries
    0.82
    tex
    0.81
    rament
    0.80
    orious
    0.80
    rary
    0.80
    Activations Density 0.005%

    No Known Activations